Bearprompt logo Bearprompt
Back to Jev
jev-latest Score
How to run jev-latest

Score a Safari crash

Description

TypeSafe’s Score example: how severe a Safari-only export crash is on a three-level rubric.

Copy

from typesafe_sdk import Choice, Noul, Score, TypeSafeClient

with TypeSafeClient(model="jev-latest") as client:
    result = client.system_one(
        state="The export button crashes the settings page in Safari. It works in Chrome, but a few of our customers only use Safari.",
        questions={
            "bug_severity": Score(
                instructions="How severe is the reported issue?",
                criteria=[
                "Cosmetic; no impact to functionality",
                "Broken or degraded feature, but workaround exists",
                "Blocking issue; no workaround exists"
            ],
            )
        },
    )

Worked example

Illustrative for this sample state, not a live run

Sample state

The export button crashes the settings page in Safari. It works in Chrome, but a few of our customers only use Safari.
Score bug_severity

How severe is the reported issue?

Score 1.43 on 0–2

  • 0. Cosmetic; no impact to functionality 0%
  • 1. Broken or degraded feature, but workaround exists 57%
  • 2. Blocking issue; no workaround exists 43%

Confidence 35%

What you might do next

A score of 1.43 sits between “workaround exists” (0.57) and “no workaround” (0.43). Rank reports by score, or round to the nearest level when the code needs one outcome.

Tags

scoreincident
Loading...